NVIDIA H100 SXMvsNVIDIA B200
Detailed specifications, performance benchmarks, and pricing comparison to help you choose the right GPU for your AI workloads.
NVIDIA H100 SXM
Hopper · 2022
NVIDIA B200
Blackwell · 2024
Specifications · Comparison
Side by side specs.
| Spec | NVIDIA H100 SXM | NVIDIA B200 |
|---|---|---|
| Architecture | Hopper | Blackwell |
| VRAM | 80 GB | 192 GB+58.3% |
| Memory Type | HBM3 | HBM3e |
| Memory Bandwidth | 3350 GB/s | 8000 GB/s+58.1% |
| FP32 Performance | 60 TFLOPS | 90 TFLOPS+33.3% |
| FP16 Performance | 120 TFLOPS | 180 TFLOPS+33.3% |
| INT8 Performance | 2400 TOPS | 3600 TOPS+33.3% |
| TDP | 700W | 1000W |
| Form Factor | SXM | SXM |
| Price (avg/hr) | $1.50 | $3.40 |
Performance · Analysis
Performance breakdown.
Compute (FP32)
Raw single-precision floating point throughput
NVIDIA B200 is 33.3% faster
Training (FP16)
Half-precision performance for deep learning training
NVIDIA B200 is 33.3% faster
Inference (INT8)
Integer performance for model inference workloads
NVIDIA B200 is 33.3% faster
Memory Bandwidth
Data transfer rate between memory and compute units
NVIDIA B200 is 58.1% faster
Best Compute
NVIDIA B200
Most Memory
NVIDIA B200
Best Training
NVIDIA B200
Best Value
NVIDIA H100 SXM
Pricing · Cost
Cost comparison.
Hourly
Save $1.90 with NVIDIA H100 SXM
Daily
Save $45.60 with NVIDIA H100 SXM
Monthly
Save $1368.00 with NVIDIA H100 SXM
Use Cases · Workloads
Best for your workload.
NVIDIA H100 SXM
NVIDIA B200
Platform · Benefits
Why Runcrate.
Instant Deployment
Get your GPU instance running in minutes with pre-configured AI environments. No setup complexity.
Pay Per Hour
Only pay for the compute you actually use. Prepaid credits with transparent, per-hour billing.
Reliable Infrastructure
Enterprise-grade reliability with automatic failover and data persistence across sessions.
Related · Comparisons
Compare other GPUs.
FAQ · Questions
Common questions.
Deploy NVIDIA H100 SXM or NVIDIA B200
Get started with GPU cloud computing in minutes. No setup complexity, no long-term commitments.